[dev.simd] simd, cmd/compile: move "simd" to "simd/archsimd"

Also removes a few leftover TODOs and scraps of commented-out code
from simd development.

Updated etetest.sh to make it behave whether amd64 implies the
experiment, or not.

Fixes #76473.

Change-Id: I6d9792214d7f514cb90c21b101dbf7d07c1d0e55
Reviewed-on: https://go-review.googlesource.com/c/go/+/728220
TryBot-Bypass: David Chase <[email protected]>
Reviewed-by: Cherry Mui <[email protected]>

Author: dr2chase

src/cmd/compile/internal/inline/inl.go

@@ -445,7 +445,7 @@ type hairyVisitor struct {
 
 func isDebugFn(fn *ir.Func) bool {
 	// if n := fn.Nname; n != nil {
-	// 	if n.Sym().Name == "Int32x8.Transpose8" && n.Sym().Pkg.Path == "simd" {
+	// 	if n.Sym().Name == "Int32x8.Transpose8" && n.Sym().Pkg.Path == "simd/archsimd" {
 	// 		fmt.Printf("isDebugFn '%s' DOT '%s'\n", n.Sym().Pkg.Path, n.Sym().Name)
 	// 		return true
 	// 	}

src/cmd/compile/internal/ssagen/intrinsics.go

@@ -1644,7 +1644,7 @@ func initIntrinsics(cfg *intrinsicBuildConfig) {
 		// Only enable intrinsics, if SIMD experiment.
 		simdIntrinsics(addF)
 
-		addF("simd", "ClearAVXUpperBits",
+		addF(simdPackage, "ClearAVXUpperBits",
 			func(s *state, n *ir.CallExpr, args []*ssa.Value) *ssa.Value {
 				s.vars[memVar] = s.newValue1(ssa.OpAMD64VZEROUPPER, types.TypeMem, s.mem())
 				return nil
@@ -1668,15 +1668,18 @@ func initIntrinsics(cfg *intrinsicBuildConfig) {
 		addF(simdPackage, "Uint32x8.IsZero", opLen1(ssa.OpIsZeroVec, types.Types[types.TBOOL]), sys.AMD64)
 		addF(simdPackage, "Uint64x4.IsZero", opLen1(ssa.OpIsZeroVec, types.Types[types.TBOOL]), sys.AMD64)
 
+		// sfp4 is intrinsic-if-constant, but otherwise it's complicated enough to just implement in Go.
 		sfp4 := func(method string, hwop ssa.Op, vectype *types.Type) {
-			addF("simd", method,
+			addF(simdPackage, method,
 				func(s *state, n *ir.CallExpr, args []*ssa.Value) *ssa.Value {
 					x, a, b, c, d, y := args[0], args[1], args[2], args[3], args[4], args[5]
 					if a.Op == ssa.OpConst8 && b.Op == ssa.OpConst8 && c.Op == ssa.OpConst8 && d.Op == ssa.OpConst8 {
-						return select4FromPair(x, a, b, c, d, y, s, hwop, vectype)
-					} else {
-						return s.callResult(n, callNormal)
+						z := select4FromPair(x, a, b, c, d, y, s, hwop, vectype)
+						if z != nil {
+							return z
+						}
 					}
+					return s.callResult(n, callNormal)
 				},
 				sys.AMD64)
 		}
@@ -1693,15 +1696,18 @@ func initIntrinsics(cfg *intrinsicBuildConfig) {
 		sfp4("Uint32x16.SelectFromPairGrouped", ssa.OpconcatSelectedConstantGroupedUint32x16, types.TypeVec512)
 		sfp4("Float32x16.SelectFromPairGrouped", ssa.OpconcatSelectedConstantGroupedFloat32x16, types.TypeVec512)
 
+		// sfp2 is intrinsic-if-constant, but otherwise it's complicated enough to just implement in Go.
 		sfp2 := func(method string, hwop ssa.Op, vectype *types.Type, cscimm func(i, j uint8) int64) {
-			addF("simd", method,
+			addF(simdPackage, method,
 				func(s *state, n *ir.CallExpr, args []*ssa.Value) *ssa.Value {
 					x, a, b, y := args[0], args[1], args[2], args[3]
 					if a.Op == ssa.OpConst8 && b.Op == ssa.OpConst8 {
-						return select2FromPair(x, a, b, y, s, hwop, vectype, cscimm)
-					} else {
-						return s.callResult(n, callNormal)
+						z := select2FromPair(x, a, b, y, s, hwop, vectype, cscimm)
+						if z != nil {
+							return z
+						}
 					}
+					return s.callResult(n, callNormal)
 				},
 				sys.AMD64)
 		}
@@ -1767,6 +1773,9 @@ const (
 
 func select2FromPair(x, _a, _b, y *ssa.Value, s *state, op ssa.Op, t *types.Type, csc func(a, b uint8) int64) *ssa.Value {
 	a, b := uint8(_a.AuxInt8()), uint8(_b.AuxInt8())
+	if a > 3 || b > 3 {
+		return nil
+	}
 	pattern := (a&2)>>1 + (b & 2)
 	a, b = a&1, b&1
 
@@ -1785,6 +1794,9 @@ func select2FromPair(x, _a, _b, y *ssa.Value, s *state, op ssa.Op, t *types.Type
 
 func select4FromPair(x, _a, _b, _c, _d, y *ssa.Value, s *state, op ssa.Op, t *types.Type) *ssa.Value {
 	a, b, c, d := uint8(_a.AuxInt8()), uint8(_b.AuxInt8()), uint8(_c.AuxInt8()), uint8(_d.AuxInt8())
+	if a > 7 || b > 7 || c > 7 || d > 7 {
+		return nil
+	}
 	pattern := a>>2 + (b&4)>>1 + (c & 4) + (d&4)<<1
 
 	a, b, c, d = a&3, b&3, c&3, d&3
@@ -2154,7 +2166,7 @@ func findIntrinsic(sym *types.Sym) intrinsicBuilder {
 	fn := sym.Name
 	if ssa.IntrinsicsDisable {
 		if pkg == "internal/runtime/sys" && (fn == "GetCallerPC" || fn == "GrtCallerSP" || fn == "GetClosurePtr") ||
-			pkg == "internal/simd" || pkg == "simd" { // TODO after simd has been moved to package simd, remove internal/simd
+			pkg == simdPackage {
 			// These runtime functions don't have definitions, must be intrinsics.
 		} else {
 			return nil

src/cmd/compile/internal/ssagen/intrinsics_test.go

@@ -1407,13 +1407,13 @@ func TestIntrinsics(t *testing.T) {
 		gotIntrinsics[testIntrinsicKey{ik.arch.Name, ik.pkg, ik.fn}] = struct{}{}
 	}
 	for ik, _ := range gotIntrinsics {
-		if _, found := wantIntrinsics[ik]; !found && (ik.pkg != "simd" || *simd) {
+		if _, found := wantIntrinsics[ik]; !found && (ik.pkg != "simd/archsimd" || *simd) {
 			t.Errorf("Got unwanted intrinsic %v %v.%v", ik.archName, ik.pkg, ik.fn)
 		}
 	}
 
 	for ik, _ := range wantIntrinsics {
-		if _, found := gotIntrinsics[ik]; !found && (ik.pkg != "simd" || *simd) {
+		if _, found := gotIntrinsics[ik]; !found && (ik.pkg != "simd/archsimd" || *simd) {
 			t.Errorf("Want missing intrinsic %v %v.%v", ik.archName, ik.pkg, ik.fn)
 		}
 	}

src/cmd/compile/internal/ssagen/simdintrinsics.go

@@ -471,11 +471,6 @@ func simdify(st *Type, isTag bool) {
 	} else {
 		st.floatRegs = 1
 	}
-	// if st.Sym() != nil {
-	// 	base.Warn("Simdify %s, %v, %d", st.Sym().Name, isTag, st.width)
-	// } else {
-	// 	base.Warn("Simdify %v, %v, %d", st, isTag, st.width)
-	// }
 }
 
 // CalcStructSize calculates the size of t,
@@ -491,10 +486,9 @@ func CalcStructSize(t *Type) {
 		case sym.Name == "align64" && isAtomicStdPkg(sym.Pkg):
 			maxAlign = 8
 
-		case buildcfg.Experiment.SIMD && (sym.Pkg.Path == "internal/simd" || sym.Pkg.Path == "simd") && len(t.Fields()) >= 1:
+		case buildcfg.Experiment.SIMD && (sym.Pkg.Path == "simd/archsimd") && len(t.Fields()) >= 1:
 			// This gates the experiment -- without it, no user-visible types can be "simd".
 			// The SSA-visible SIMD types remain.
-			// TODO after simd has been moved to package simd, remove internal/simd.
 			switch sym.Name {
 			case "v128":
 				simdify(t, true)

src/cmd/compile/internal/types/size.go

@@ -361,8 +361,8 @@ var excluded = map[string]bool{
 	"builtin":                       true,
 	"cmd/compile/internal/ssa/_gen": true,
 	"runtime/_mkmalloc":             true,
-	"simd/_gen/simdgen":             true,
-	"simd/_gen/unify":               true,
+	"simd/archsimd/_gen/simdgen":    true,
+	"simd/archsimd/_gen/unify":      true,
 }
 
 // printPackageMu synchronizes the printing of type-checked package files in

src/cmd/compile/internal/types2/stdlib_test.go

@@ -73,7 +73,7 @@ var depsRules = `
 	internal/byteorder, internal/cpu, internal/goarch < internal/chacha8rand;
 	internal/goarch, math/bits < internal/strconv;
 
-	internal/cpu, internal/strconv < simd;
+	internal/cpu, internal/strconv < simd/archsimd;
 
 	# RUNTIME is the core runtime group of packages, all of them very light-weight.
 	internal/abi,
@@ -709,7 +709,7 @@ var depsRules = `
 	< testing;
 
 	testing, math
-	< simd/internal/test_helpers;
+	< simd/archsimd/internal/test_helpers;
 
 	log/slog, testing
 	< testing/slogtest;

src/go/build/deps_test.go

@@ -361,8 +361,8 @@ var excluded = map[string]bool{
 	"builtin":                       true,
 	"cmd/compile/internal/ssa/_gen": true,
 	"runtime/_mkmalloc":             true,
-	"simd/_gen/simdgen":             true,
-	"simd/_gen/unify":               true,
+	"simd/archsimd/_gen/simdgen":    true,
+	"simd/archsimd/_gen/unify":      true,
 }
 
 // printPackageMu synchronizes the printing of type-checked package files in

src/go/types/stdlib_test.go

@@ -1,4 +1,4 @@
-module simd/_gen
+module simd/archsimd/_gen
 
 go 1.24